frappe-agent-migrator

Warn

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use CLI tools including bench, git, and grep for environment discovery and code analysis. These are essential for the migration workflow.- [COMMAND_EXECUTION]: Migration and rollback procedures include the use of sudo supervisorctl to restart system services. This involves privilege escalation, which is a standard requirement for managing Frappe production environments but carries inherent risk.- [PROMPT_INJECTION]: The skill analyzes custom application source code to detect deprecated patterns. This introduces an indirect prompt injection surface where external data could influence agent behavior.
  • Ingestion points: Output from grep commands targeting custom application files in SKILL.md Step 3.
  • Boundary markers: The instructions do not define specific delimiters or markers to isolate the audited code from agent instructions.
  • Capability inventory: The agent is authorized to perform database migrations, backup/restore operations, and service management via sudo.
  • Sanitization: No validation or sanitization of the scanned file content is specified.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 14, 2026, 09:39 AM
Security Audit — agent-trust-hub — frappe-agent-migrator